Internship / Master Thesis - VLAMs for Trajectory Prediction (m/f/d)
Internship / Master Thesis - VLAMs for Trajectory Prediction (m/f/d)
München, DE, 80807
Internship / Master Thesis - VLAMs for Trajectory Prediction (m/f/d)
We are CARIAD, the automotive software company of the Volkswagen Group. Our teams build automotive software platforms and digital customer functions for iconic brands like Audi, Volkswagen, and Porsche – supporting the Volkswagen Group in becoming the leading automotive technology company. With CARIDIANS in Germany, the USA, China, Estonia, and India, we are transforming automotive mobility for everyone.
Join us and be part of this exciting journey!
YOUR TEAM
We offer you an exciting opportunity for your master thesis or for an internship in our ADAS/AD – VLAM team in in the field of model engineering for autonomous driving. For the following topic you get the responsibility: multimodal trajectory prediction with Visual-Language-Action models (VLAMs). The aim of this master thesis / the internship is to explore how large, pretrained multimodal foundation models can:
(1) provide rich scene and intent representation,
(2) represent latent and uncertain dynamics, and
(3) generate accurate, diverse, uncertainty-aware agent trajectory forecasts that can be used for downstream vehicle control.
The department works on software and machine learning models for automated driving (AD) in urban environments, with a focus on the use of foundation models for end-to-end training. Within this department, we are a team of ambitious and highly motivated experts in the field of self-driving vehicles working in an agile environment to advance the autonomous driving stack.
WHAT YOU WILL DO
- Research and assess the state-of-the-art of visual-language-action models for autonomous driving
- Develop and refine model architectures focused on outputting diverse, probabilistic, and plausible future trajectories rather than a single deterministic path.
- Conduct extensive experiments on public and internal datasets
- Investigate the limitations of open-loop evaluation on standard datasets that inherently contain only a single realized future (one ground truth).
- Work closely with our PhD students and the model engineering team
WHO YOU ARE
- Master student in the area of Computer Science, Robotics, Mechatronics Engineering, Electrical Engineering or similar
- Good general knowledge in the field of (self-)supervised learning, transformer-based architectures, and (vision) foundation models
- Very good knowledge of machine learning frameworks such as PyTorch and applied knowledge in software development and programming in Python or C++
- Structured and independent work, above-average commitment and flexibility
- Strong communication skills and analytical understanding
NICE TO KNOW
- Remote work options within Germany
- Duration: 3 - 6 months
- 35 hours/week
- Salary: 13,90 €/hour
At CARIAD, we embrace individuality and diversity because we believe our differences make us stronger. We actively seek to build teams with a variety of backgrounds, perspectives, and experiences. Our goal is to create an environment where everyone feels valued and empowered to contribute. If you need assistance with your application due to a disability, please reach out to us at careers@cariad.technology - we are happy to support you.
We are CARIAD, the automotive software company of the Volkswagen Group. Our teams build automotive software platforms and digital customer functions for iconic brands like Audi, Volkswagen, and Porsche – supporting the Volkswagen Group in becoming the leading automotive technology company. With CARIDIANS in Germany, the USA, China, Estonia, and India, we are transforming automotive mobility for everyone.
Join us and be part of this exciting journey!
YOUR TEAM
We offer you an exciting opportunity for your master thesis or for an internship in our ADAS/AD – VLAM team in in the field of model engineering for autonomous driving. For the following topic you get the responsibility: multimodal trajectory prediction with Visual-Language-Action models (VLAMs). The aim of this master thesis / the internship is to explore how large, pretrained multimodal foundation models can:
(1) provide rich scene and intent representation,
(2) represent latent and uncertain dynamics, and
(3) generate accurate, diverse, uncertainty-aware agent trajectory forecasts that can be used for downstream vehicle control.
The department works on software and machine learning models for automated driving (AD) in urban environments, with a focus on the use of foundation models for end-to-end training. Within this department, we are a team of ambitious and highly motivated experts in the field of self-driving vehicles working in an agile environment to advance the autonomous driving stack.
WHAT YOU WILL DO
- Research and assess the state-of-the-art of visual-language-action models for autonomous driving
- Develop and refine model architectures focused on outputting diverse, probabilistic, and plausible future trajectories rather than a single deterministic path.
- Conduct extensive experiments on public and internal datasets
- Investigate the limitations of open-loop evaluation on standard datasets that inherently contain only a single realized future (one ground truth).
- Work closely with our PhD students and the model engineering team
WHO YOU ARE
- Master student in the area of Computer Science, Robotics, Mechatronics Engineering, Electrical Engineering or similar
- Good general knowledge in the field of (self-)supervised learning, transformer-based architectures, and (vision) foundation models
- Very good knowledge of machine learning frameworks such as PyTorch and applied knowledge in software development and programming in Python or C++
- Structured and independent work, above-average commitment and flexibility
- Strong communication skills and analytical understanding
NICE TO KNOW
- Remote work options within Germany
- Duration: 3 - 6 months
- 35 hours/week
- Salary: 13,90 €/hour
At CARIAD, we embrace individuality and diversity because we believe our differences make us stronger. We actively seek to build teams with a variety of backgrounds, perspectives, and experiences. Our goal is to create an environment where everyone feels valued and empowered to contribute. If you need assistance with your application due to a disability, please reach out to us at careers@cariad.technology - we are happy to support you.
München, DE, 80807